{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GUQPO24OHVTA7D7N5WYCVR4P5A","short_pith_number":"pith:GUQPO24O","canonical_record":{"source":{"id":"2105.01279","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-04T04:08:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"510595a3011b6489ef96281b63f54ff019236b750c35b0b501275b1b3c8497da","abstract_canon_sha256":"d69ecd1e4b26a9e179b8e1ee59c6b76398543c1f16b425429caa4d6696886fc5"},"schema_version":"1.0"},"canonical_sha256":"3520f76b8e3d660f8fededb02ac78fe812e056968d860d5525602d065dcf2a84","source":{"kind":"arxiv","id":"2105.01279","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.01279","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2105.01279v1","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01279","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"GUQPO24OHVTA","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"GUQPO24OHVTA7D7N","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"GUQPO24O","created_at":"2026-07-05T02:37:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GUQPO24OHVTA7D7N5WYCVR4P5A","target":"record","payload":{"canonical_record":{"source":{"id":"2105.01279","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-04T04:08:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"510595a3011b6489ef96281b63f54ff019236b750c35b0b501275b1b3c8497da","abstract_canon_sha256":"d69ecd1e4b26a9e179b8e1ee59c6b76398543c1f16b425429caa4d6696886fc5"},"schema_version":"1.0"},"canonical_sha256":"3520f76b8e3d660f8fededb02ac78fe812e056968d860d5525602d065dcf2a84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:15.410117Z","signature_b64":"Sw2CyhF/1MwSiEgqYgsm17kqAVve804BDQKGqPVyEg+QOMnlutN+Z71RNHyMYeWisCrRJMbymTePEeULDn8jCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3520f76b8e3d660f8fededb02ac78fe812e056968d860d5525602d065dcf2a84","last_reissued_at":"2026-07-05T02:37:15.409554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:15.409554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.01279","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:37:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x/I/NDTPqDtvViJCqfRAMVzXGzS6CwG5Lx5xoWhH+b5xmSczN7FQi8W8EVkAu9rxhqt+yRMjrlFE8vYkmdaYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:54:03.968401Z"},"content_sha256":"f33a0b5948d9eb71b246e5b5dcea8c0d273dfacbd206719bd002db9f5b8f0185","schema_version":"1.0","event_id":"sha256:f33a0b5948d9eb71b246e5b5dcea8c0d273dfacbd206719bd002db9f5b8f0185"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GUQPO24OHVTA7D7N5WYCVR4P5A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kai-Fu Lee, Tong Zhang, Yan Song, Yonggang Wang","submitted_at":"2021-05-04T04:08:58Z","abstract_excerpt":"Pre-trained text encoders have drawn sustaining attention in natural language processing (NLP) and shown their capability in obtaining promising results in different tasks. Recent studies illustrated that external self-supervised signals (or knowledge extracted by unsupervised learning, such as n-grams) are beneficial to provide useful semantic evidence for understanding languages such as Chinese, so as to improve the performance on various downstream tasks accordingly. To further enhance the encoders, in this paper, we propose to pre-train n-gram-enhanced encoders with a large volume of data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01279","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.01279/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:37:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5WmKLhzHUUOgZMYyG5/Fy+LK6QBzxNYO3yQ3GFjSH8hrtdTQ/+fD91vrKQJRzTR54L9xAc1lFcumxspVKYAsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:54:03.969302Z"},"content_sha256":"0d332ee94f00504f62aeb46acfbc8d0cdf0921d08d197f56e9c82ab395adca89","schema_version":"1.0","event_id":"sha256:0d332ee94f00504f62aeb46acfbc8d0cdf0921d08d197f56e9c82ab395adca89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/bundle.json","state_url":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T16:54:03Z","links":{"resolver":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A","bundle":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/bundle.json","state":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GUQPO24OHVTA7D7N5WYCVR4P5A","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d69ecd1e4b26a9e179b8e1ee59c6b76398543c1f16b425429caa4d6696886fc5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-04T04:08:58Z","title_canon_sha256":"510595a3011b6489ef96281b63f54ff019236b750c35b0b501275b1b3c8497da"},"schema_version":"1.0","source":{"id":"2105.01279","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.01279","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2105.01279v1","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01279","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"GUQPO24OHVTA","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"GUQPO24OHVTA7D7N","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"GUQPO24O","created_at":"2026-07-05T02:37:15Z"}],"graph_snapshots":[{"event_id":"sha256:0d332ee94f00504f62aeb46acfbc8d0cdf0921d08d197f56e9c82ab395adca89","target":"graph","created_at":"2026-07-05T02:37:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2105.01279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained text encoders have drawn sustaining attention in natural language processing (NLP) and shown their capability in obtaining promising results in different tasks. Recent studies illustrated that external self-supervised signals (or knowledge extracted by unsupervised learning, such as n-grams) are beneficial to provide useful semantic evidence for understanding languages such as Chinese, so as to improve the performance on various downstream tasks accordingly. To further enhance the encoders, in this paper, we propose to pre-train n-gram-enhanced encoders with a large volume of data ","authors_text":"Kai-Fu Lee, Tong Zhang, Yan Song, Yonggang Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-04T04:08:58Z","title":"ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01279","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f33a0b5948d9eb71b246e5b5dcea8c0d273dfacbd206719bd002db9f5b8f0185","target":"record","created_at":"2026-07-05T02:37:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d69ecd1e4b26a9e179b8e1ee59c6b76398543c1f16b425429caa4d6696886fc5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-04T04:08:58Z","title_canon_sha256":"510595a3011b6489ef96281b63f54ff019236b750c35b0b501275b1b3c8497da"},"schema_version":"1.0","source":{"id":"2105.01279","kind":"arxiv","version":1}},"canonical_sha256":"3520f76b8e3d660f8fededb02ac78fe812e056968d860d5525602d065dcf2a84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3520f76b8e3d660f8fededb02ac78fe812e056968d860d5525602d065dcf2a84","first_computed_at":"2026-07-05T02:37:15.409554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:15.409554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sw2CyhF/1MwSiEgqYgsm17kqAVve804BDQKGqPVyEg+QOMnlutN+Z71RNHyMYeWisCrRJMbymTePEeULDn8jCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:15.410117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.01279","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f33a0b5948d9eb71b246e5b5dcea8c0d273dfacbd206719bd002db9f5b8f0185","sha256:0d332ee94f00504f62aeb46acfbc8d0cdf0921d08d197f56e9c82ab395adca89"],"state_sha256":"f141a99c180ba9e4cfe9a80fc9cb9481d32424038326f3e804598e294506fff7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEmpLz4hy+qf/ucvTh3gywZb50b9bg4INtFpWewFk3sZi4t+YHnZjvOtTQQseGvq2RKmpKc6qvjhEt0dUmCXCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:54:03.975108Z","bundle_sha256":"e68bdc89b5067d687c9511bbe49c61c0d31ade19faae1eb95f2f2bb25760f849"}}